© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 85412
    Prev
    Next
    INDEX
    Explanations

    condemn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ")
↵
    -0.07
    增强
    -0.07
     receive
    -0.07
    _checked
    -0.07
    Link
    -0.06
     delve
    -0.06
     Holl
    -0.06
    '"↵
    -0.06
    ↵	
↵
    -0.06
     populated
    -0.06
    POSITIVE LOGITS
    грани
    0.07
     resil
    0.07
    (article
    0.07
    -custom
    0.07
    嫁给
    0.07
    .Hide
    0.07
    .finished
    0.07
     kay
    0.07
    _times
    0.07
    rés
    0.06
    Activations Density 0.056%

    No Known Activations